Skip to main content
Open source · MLflow native · Framework agnostic

Trust your agents.
Verify with evidence.

Agent Lens is the conversational quality gate for MLflow. Evaluate, qualify, and govern your agent fleet — in plain English. Works with any framework: LangGraph, Google ADK, LangChain, CrewAI, OpenAI Agents SDK, and more.

Up and running in minutes.

# Clone and verify locally
$ git clone https://github.com/rrbanda/agentlens && cd agentlens
$ make dev-setup && make mlflow-start
$ make seed-data && make test-integration
41 passed in 12.4s

# Deploy to Kubernetes
$ make deploy-all && make status
agent-lens 1/1 Running 0 49s

Everything you need to
qualify your agent fleet.

🔍

Conversational Evaluation

Ask "Can this agent be deployed?" and get a structured qualification verdict with evidence. No Python scripts required.

MLflow MCP Native

Built entirely on the official MLflow MCP server. Zero custom forks. Your data stays in MLflow.

🔒

Sandboxed and Secure

Runs inside an OpenShell sandbox with defense-in-depth isolation — Linux namespaces, Landlock, seccomp, L7 network proxy. The qualification agent itself is constrained, not just the agents it evaluates.

🔌

Pick Your Harness

Skills are portable markdown — not code. Ships with two validated harnesses (Hermes + Google ADK), works with Claude Code, OpenClaw, Goose, or any MCP-capable runtime.

🛡️

Red-Team Safety

Test for prompt injection, data exfiltration, jailbreaks, and PII leakage with attack-specific judges.

📊

EDD Loop

Evaluation-Driven Development: baseline, diagnose failures, fix, re-evaluate, compare. The full MLflow cookbook workflow — conversational.

⚖️

Cost-Quality Tradeoff

Compare quality vs cost across models and configurations. Find the optimal tradeoff for your budget.

🧪

Custom Judges

Create domain-specific LLM judges from natural language. "Check if the agent mentions our privacy policy" becomes a registered scorer.

🏷️

Qualification Verdicts

>=80% scorer pass rate + <5% error rate = QUALIFIED. Evidence-based decisions, not gut feelings.

🌐

Framework Agnostic

Evaluates any agent that sends traces to MLflow — LangGraph, Google ADK, LangChain, CrewAI, OpenAI Agents SDK, AutoGen, or custom.

Built-in skills for every stage of qualification.

SkillMCP Tools
trace-explorer
Search and drill into any trace
search_experiments, search_traces, get_trace
quality-dashboard
Fleet-wide health + cost + latency
search_experiments, search_traces, list_runs
analyze-session
Trace analysis with status and latency
search_traces, get_trace
review-trace
Deep-dive + assessments
get_trace, get_trace_assessment
create-regression
Flag failures for follow-up
update_trace_assessment, set_trace_tag
evaluate-agent
Run LLM judges on traces
list_scorers, evaluate_traces
compare-evaluations
Track quality over time
list_runs, describe_run
create-judge
Build custom scorers from English
list_scorers, register_llm_judge_scorer
red-team
Adversarial safety evaluation
search_traces, evaluate_traces
eval-loop
Full EDD improvement cycle
create_run, search_traces
cost-quality
Cost vs quality tradeoff analysis
list_runs, describe_run, search_traces
audit-trail
Qualification decision history
search_traces, list_runs, describe_run
agent-registry
Fleet inventory and status
search_experiments, list_runs, describe_run
executive-summary
Board-ready health summary
search_experiments, search_traces, list_runs
compliance-export
JSONL/CSV export for GRC tools
search_traces, list_runs, describe_run
aggregate-traces
Error rates, latency, token trends
search_traces

Stop guessing if your agents work.

Open source. Self-hosted. Framework-agnostic. Runs on any Kubernetes cluster with MLflow.